Harmonised LUCAS in-situ land cover and use database for field surveys from 2006 to 2018 in the European Union

Unlocking ground-based imagery for habitat mapping

Fine-grained environmental data across large extents are needed to resolve the processes that impact species communities from local to global scales. Ground-based images (GBIs) have the potential to capture habitat complexity at biologically relevant spatial and temporal resolutions. Moving beyond existing applications of GBIs for species identification and monitoring ecological change from repeat photography, we describe promising approaches to habitat mapping, leveraging multimodal data and computer vision. We illustrate empirically how GBIs can be applied to predict distributions of species at fine scales along Street View routes, or to automatically classify and quantify habitat features. Further, we outline future research avenues using GBIs that can bring a leap forward in analyses for ecology and conservation with this underused resource.

Biotic homogenization, lower soil fungal diversity and fewer rare taxa in arable soils across Europe

Soil fungi are a key constituent of global biodiversity and play a pivotal role in agroecosystems. How arable farming affects soil fungal biogeography and whether it has a disproportional impact on rare taxa is poorly understood. Here, we used the high-resolution PacBio Sequel targeting the entire ITS region to investigate the distribution of soil fungi in 217 sites across a 3000 km gradient in Europe. We found a consistently lower diversity of fungi in arable lands than grasslands, with geographic locations significantly impacting fungal community structures. Prevalent fungal groups became even more abundant, whereas rare groups became fewer or absent in arable lands, suggesting a biotic homogenization due to arable farming. The rare fungal groups were narrowly distributed and more common in grasslands. Our findings suggest that rare soil fungi are disproportionally affected by arable farming, and sustainable farming practices should protect rare taxa and the ecosystem services they support.

A global land cover training dataset from 1984 to 2020

State-of-the-art cloud computing platforms such as Google Earth Engine (GEE) enable regional-to-global land cover and land cover change mapping with machine learning algorithms. However, collection of high-quality training data, which is necessary for accurate land cover mapping, remains costly and labor-intensive. To address this need, we created a global database of nearly 2 million training units spanning the period from 1984 to 2020 for seven primary and nine secondary land cover classes. Our training data collection approach leveraged GEE and machine learning algorithms to ensure data quality and biogeographic representation. We sampled the spectral-temporal feature space from Landsat imagery to efficiently allocate training data across global ecoregions and incorporated publicly available and collaborator-provided datasets to our database. To reflect the underlying regional class distribution and post-disturbance landscapes, we strategically augmented the database. We used a machine learning-based cross-validation procedure to remove potentially mis-labeled training units. Our training database is relevant for a wide array of studies such as land cover change, agriculture, forestry, hydrology, urban development, among many others.

A detailed land use/land cover map for the European Alps macro region

Spatially and thematically detailed land use maps are of special importance to study and manage populated mountain regions. Due to the complex terrain, high elevational gradients as well as differences in land demand, these regions are characterized by a high density of different land uses that form heterogeneous landscapes. Here, we present a new highly detailed land use/landcover map for the areas included in the European Strategy for the Alpine Region. The map has a spatial resolution of up to 5 m and a temporal extent from 2015 to 2020. It was created by aggregating 15 high-resolution layers resulting in 65 land use/cover classes. The overall map accuracy was assessed at 88.8%. The large number of land use classes and the high spatial resolution allow an easy customization of the map for research and management purposes, making it useable by a broad audience for various applications. Our map shows that by combining theme specific "high-resolution" land use products to build a comprehensive land use/land cover map, a high thematic and spatial detail can be achieved.

Ecodatacube.eu: analysis-ready open environmental data cube for Europe

The article describes the production steps and accuracy assessment of an analysis-ready, open-access European data cube consisting of 2000-2020+ Landsat data, 2017-2021+ Sentinel-2 data and a 30 m resolution digital terrain model (DTM). The main purpose of the data cube is to make annual continental-scale spatiotemporal machine learning tasks accessible to a wider user base by providing a spatially and temporally consistent multidimensional feature space. This has required systematic spatiotemporal harmonization, efficient compression, and imputation of missing values. Sentinel-2 and Landsat reflectance values were aggregated into four quarterly averages approximating the four seasons common in Europe (winter, spring, summer and autumn), as well as the 25th and 75th percentile, in order to retain intra-seasonal variance. Remaining missing data in the Landsat time-series was imputed with a temporal moving window median (TMWM) approach. An accuracy assessment shows TMWM performs relatively better in Southern Europe and lower in mountainous regions such as the Scandinavian Mountains, the Alps, and the Pyrenees. We quantify the usability of the different component data sets for spatiotemporal machine learning tasks with a series of land cover classification experiments, which show that models utilizing the full feature space (30 m DTM, 30 m Landsat, 30 m and 10 m Sentinel-2) yield the highest land cover classification accuracy, with different data sets improving the results for different land cover classes. The data sets presented in the article are part of the EcoDataCube platform, which also hosts open vegetation, soil, and land use/land cover (LULC) maps created. All data sets are available under CC-BY license as Cloud-Optimized GeoTIFFs (ca. 12 TB in size) through SpatioTemporal Asset Catalog (STAC) and the EcoDataCube data portal.

ELULC-10, a 10 m European Land Use and Land Cover Map Using Sentinel and Landsat Data in Google Earth Engine

Land Use/Land Cover (LULC) maps can be effectively produced by cost-effective and frequent satellite observations. Powerful cloud computing platforms are emerging as a growing trend in the high utilization of freely accessible remotely sensed data for LULC mapping over large-scale regions using big geodata. This study proposes a workflow to generate a 10 m LULC map of Europe with nine classes, ELULC-10, using European Sentinel-1/-2 and Landsat-8 images, as well as the LUCAS reference samples. More than 200 K and 300 K of in situ surveys and images, respectively, were employed as inputs in the Google Earth Engine (GEE) cloud computing platform to perform classification by an object-based segmentation algorithm and an Artificial Neural Network (ANN). A novel ANN-based data preparation was also presented to remove noisy reference samples from the LUCAS dataset. Additionally, the map was improved using several rule-based post-processing steps. The overall accuracy and kappa coefficient of 2021 ELULC-10 were 95.38% and 0.94, respectively. A detailed report of the classification accuracies was also provided, demonstrating an accurate classification of different classes, such as Woodland and Cropland. Furthermore, rule-based post processing improved LULC class identifications when compared with current studies. The workflow could also supply seasonal, yearly, and change maps considering the proposed integration of complex machine learning algorithms and large satellite and survey data.

Open Geospatial System for LUCAS In Situ Data Harmonization and Distribution

The use of in situ references in Earth observation monitoring is a fundamental need. LUCAS (Land Use and Coverage Area frame Survey) is an activity which has performed repeated in situ surveys over Europe every three years since 2006. The dataset is unique in many aspects, however it is currently not available through a standardized interface, machine-to-machine. Moreover, the evolution of the surveys limits the change analysis with the dataset. Our goal was to develop an open-source system to fill these gaps. This paper presents a developed system solution for the LUCAS in situ data harmonization and distribution. We have designed a multi-layer client-server system which can be integrated into end-to-end workflows. It provides data through an OGC (Open Geospatial Consortium) compliant interface. Moreover, a geospatial user can integrate the data through a Python API (Application Programming Interface) to ease the use in the workflows with spatial, temporal, attribute, and thematic filters. On top of that, we have implemented a QGIS plugin to retrieve the spatio-temporal subsets of the data interactively. Additionally, the Python API includes methods to manage thematic information. The system provides enhanced functionality which is demonstrated in two application use cases.

Developing High-Resolution Crop Maps for Major Crops in the European Union Based on Transductive Transfer Learning and Limited Ground Data

Precise and timely information on crop spatial distribution over large areas is paramount to agricultural monitoring, food security, and policy development. Currently, automatically classifying crop types at a large scale is challenging due to the scarcity of ground data. Although previous studies have indicated that transductive transfer learning (TTL) is a promising method to address this problem, it performs poorly within regions where crop compositions and phenology differ largely. Here we transferred random forest classifiers trained in limited regions with diversified growing conditions and land covers to the rest of the study area where ground data are scarce, with more than 130,000 Sentinel-2 images processed using the Google Earth Engine (GEE) platform. We established the 10 m crop maps for four major crops (i.e., maize, rapeseed, winter, and spring Triticeae crops) across 10 European Union (EU) countries from 2018 to 2019. The final crop maps had a high accuracy with overall accuracy generally greater than 0.89, with user’s accuracy and producer’s accuracy ranging from 0.72 to 0.98. Moreover, the resulting maps were consistent with the NUTS-2 level official statistics, with R2 consistently greater than 0.9. We further analyzed the crop rotation patterns and found that the rotation intervals across these EU countries were generally at least one year. Maize was dominantly rotated with winter Triticeae crops or converted to other land covers in the following year. Rapeseed was generally grown in rotation with winter Triticeae crops, whereas the rotation patterns of winter and spring Triticeae crops were more diversified. Red Edge Position (REP) and Normalized Difference Yellow Index (NDYI) played significant roles in crop classification across the EU. This study highlights the potential of the developed TTL method for crop classification over large spatial extents where labeled data are limited and the differences in crop compositions and phenology are relatively large.

Designing a European-Wide Crop Type Mapping Approach Based on Machine Learning Algorithms Using LUCAS Field Survey and Sentinel-2 Data

One of the most challenging aspects of obtaining detailed and accurate land-use and land-cover (LULC) maps is the availability of representative field data for training and validation. In this manuscript, we evaluate the use of the Eurostat Land Use and Coverage Area frame Survey (LUCAS) 2018 data to generate a detailed LULC map with 19 crop type classes and two broad categories for woodland and shrubland, and grassland. The field data were used in combination with Copernicus Sentinel-2 (S2) satellite data covering Europe. First, spatially and temporally consistent S2 image composites of (1) spectral reflectances, (2) a selection of spectral indices, and (3) several bio-geophysical indicators were created for the year 2018. From the large number of features, the most important were selected for classification using two machine-learning algorithms (support vector machine and random forest). Results indicated that the 19 crop type classes and the two broad categories could be classified with an overall accuracy (OA) of 77.6%, using independent data for validation. Our analysis of three methods to select optimum training data showed that by selecting the most spectrally different pixels for training data, the best OA could be achieved, and this already using only 11% of the total training data. Comparing our results to a similar study using Sentinel-1 (S1) data indicated that S2 can achieve slightly better results, although the spatial coverage was slightly reduced due to gaps in S2 data. Further analysis is ongoing to leverage synergies between optical and microwave data.

Medium- (MR) and Very-High-Resolution (VHR) Image Integration through Collect Earth for Monitoring Forests and Land-Use Changes: Global Forest Survey (GFS) in the Temperate FAO Ecozone in Europe (2000–2015)

Monitoring of land use, land-use changes, and forestry (LULUCF) plays a crucial role in biodiversity and global environmental challenges. In 2015, the Food and Agriculture Organization of the United Nations (FAO) launched the Global Forest Survey (GFS) integrating medium- (MR) and very-high-resolution (VHR) images through the FAO’s Collect Earth platform. More than 11,150 plots were inventoried in the Temperate FAO ecozone in Europe to monitor LULUCF from 2000 to 2015. As a result, 2.19% (VHR) to 2.77% (MR/VHR) of the study area underwent LULUCF, including a 0.37% (VHR) to 0.43% (MR/VHR) net increase in forest lands. Collect Earth and VHR images have also (i) allowed for shaping a preliminary structure of the land-use network, showing that cropland was the land type that changed most and that cropland and grassland were the more frequent land uses that generated new forest land, (ii) shown that, in 2015, mixed and monospecific forests represented 44.3% and 46.5% of the forest land, respectively, unlike other forest sources, and (iii) shown that 14.9% of the area had been affected by disturbances, particularly wood harvesting (67.47% of the disturbed forests). According to other authors, the area showed a strong correlation between canopy mortality and reported wood removals due to the transition from past clear-cut systems to “close-to-nature” silviculture.

Continental-Scale Land Cover Mapping at 10 m Resolution Over Europe (ELC10)

Land cover maps are important tools for quantifying the human footprint on the environment and facilitate reporting and accounting to international agreements addressing the Sustainable Development Goals. Widely used European land cover maps such as CORINE (Coordination of Information on the Environment) are produced at medium spatial resolutions (100 m) and rely on diverse data with complex workflows requiring significant institutional capacity. We present a 10 m resolution land cover map (ELC10) of Europe based on a satellite-driven machine learning workflow that is annually updatable. A random forest classification model was trained on 70K ground-truth points from the LUCAS (Land Use/Cover Area Frame Survey) dataset. Within the Google Earth Engine cloud computing environment, the ELC10 map can be generated from approx. 700 TB of Sentinel imagery within approx. 4 days from a single research user account. The map achieved an overall accuracy of 90% across eight land cover classes and could account for statistical unit land cover proportions within 3.9% (R2 = 0.83) of the actual value. These accuracies are higher than that of CORINE (100 m) and other 10 m land cover maps including S2GLC and FROM-GLC10. Spectro-temporal metrics that capture the phenology of land cover classes were most important in producing high mapping accuracies. We found that the atmospheric correction of Sentinel-2 and the speckle filtering of Sentinel-1 imagery had a minimal effect on enhancing the classification accuracy (<1%). However, combining optical and radar imagery increased accuracy by 3% compared to Sentinel-2 alone and by 10% compared to Sentinel-1 alone. The addition of auxiliary data (terrain, climate and night-time lights) increased accuracy by an additional 2%. By using the centroid pixels from the LUCAS Copernicus module polygons we increased accuracy by <1%, revealing that random forests are robust against contaminated training data. Furthermore, the model requires very little training data to achieve moderate accuracies—the difference between 5K and 50K LUCAS points is only 3% (86% vs. 89%). This implies that significantly less resources are necessary for making in situ survey data (such as LUCAS) suitable for satellite-based land cover classification. At 10 m resolution, the ELC10 map can distinguish detailed landscape features like hedgerows and gardens, and therefore holds potential for aerial statistics at the city borough level and monitoring property-level environmental interventions (e.g., tree planting). Due to the reliance on purely satellite-based input data, the ELC10 map can be continuously updated independent of any country-specific geographic datasets.

What Happens in the City When Long-Term Urban Expansion and (Un)Sustainable Fringe Development Occur: The Case Study of Rome

This study investigates long-term landscape transformations (1949–2016) in urban Rome, Central Italy, through a spatial distribution of seven metrics (core, islet, perforation, edge, loop, bridge, branch) derived from a Morphological Spatial Pattern Analysis (MSPA) analyzed separately for seven land-use classes (built-up areas, arable land, crop mosaic, vineyards, olive groves, forests, pastures). A Principal Component Analysis (PCA) has been finally adopted to characterize landscape structure at 1949 and 2016. Results of the MSPA demonstrate how both natural and agricultural land-uses have decreased following urban expansion. Moreover, the percent ‘core’ area of each class declined substantially, although with different intensity. These results clearly indicate ‘winners’ and ‘losers’ after long-term landscape transformations: urban settlements and forests belong to the former category, the remaining land-use classes (mostly agricultural) belong to the latter category. Descriptive statistics and multivariate exploratory techniques finally documented the intrinsic complexity characteristic of actual landscapes. The findings of this study also demonstrate how settlements have expanded chaotically over the study area, reflecting a progressive ‘fractalization’ and inhomogeneity of fringe landscapes, with negative implications for metropolitan sustainability at large. These transformations were unable to leverage processes of settlement and economic re-agglomeration around sub-centers typical of polycentric development in the most advanced socioeconomic contexts.

Comparing land surface phenology of major European crops as derived from SAR and multispectral data of Sentinel-1 and -2

The frequent acquisitions of fine spatial resolution imagery (10 m) offered by recent multispectral satellite missions, including Sentinel-2, can resolve single agricultural fields and thus provide crop-specific phenology metrics, a crucial information for crop monitoring. However, effective phenology retrieval may still be hampered by significant cloud cover. Synthetic aperture radar (SAR) observations are not restricted by weather conditions, and Sentinel-1 thus ensures more frequent observations of the land surface. However, these data have not been systematically exploited for phenology retrieval so far. In this study, we extracted crop-specific land surface phenology (LSP) from Sentinel-1 and Sentinel-2 of major European crops (common and durum wheat, barley, maize, oats, rape and turnip rape, sugar beet, sunflower, and dry pulses) using ground-truth information from the "Copernicus module" of the Land Use/Cover Area frame statistical Survey (LUCAS) of 2018. We consistently used a single model-fit approach to retrieve LSP metrics on temporal profiles of CR (Cross Ratio, the ratio of the backscattering coefficient VH/VV from Sentinel-1) and NDVI (Normalized Difference Vegetation Index from Sentinel-2). Our analysis revealed that LSP retrievals from Sentinel-1 are comparable to those of Sentinel-2, particularly for winter crops. The start of season (SOS) timings, as derived from Sentinel-1 and -2, are significantly correlated (average r of 0.78 for winter and 0.46 for summer crops). The correlation is lower for end of season retrievals (EOS, r of 0.62 and 0.34). Agreement between LSP derived from Sentinel-1 and -2 varies among crop types, ranging from r = 0.89 and mean absolute error MAE = 10 days (SOS of dry pulses) to r = 0.15 and MAE = 53 days (EOS of sugar beet). Observed deviations revealed that Sentinel-1 and -2 LSP retrievals can be complementary; for example for winter crops we found that SAR detected the start of the spring growth while multispectral data is sensitive to the vegetative growth before and during winter. To test if our results correspond reasonably to in-situ data, we compared average crop-specific LSP for Germany to average phenology from ground phenological observations of 2018 gathered from the German Meteorological Service (DWD). Our study demonstrated that both Sentinel-1 and -2 can provide relevant and at times complementary LSP information at field- and crop-level.

Crowdsourcing LUCAS: Citizens Generating Reference Land Cover and Land Use Data with a Mobile App

There are many new land use and land cover (LULC) products emerging yet there is still a lack of in situ data for training, validation, and change detection purposes. The LUCAS (Land Use Cover Area frame Sample) survey is one of the few authoritative in situ field campaigns, which takes place every three years in European Union member countries. More recently, a study has considered whether citizen science and crowdsourcing could complement LUCAS survey data, e.g., through the FotoQuest Austria mobile app and crowdsourcing campaign. Although the data obtained from the campaign were promising when compared with authoritative LUCAS survey data, there were classes that were not well classified by the citizens. Moreover, the photographs submitted through the app were not always of sufficient quality. For these reasons, in the latest FotoQuest Go Europe 2018 campaign, several improvements were made to the app to facilitate interaction with the citizens contributing and to improve their accuracy in LULC identification. In addition to extending the locations from Austria to Europe, a change detection component (comparing land cover in 2018 to the 2015 LUCAS photographs) was added, as well as an improved LC decision tree. Furthermore, a near real-time quality assurance system was implemented to provide feedback on the distance to the target location, the LULC classes chosen and the quality of the photographs. Another modification was a monetary incentive scheme in which users received between 1 to 3 Euros for each successfully completed quest of sufficient quality. The purpose of this paper is to determine whether citizens can provide high quality in situ data on LULC through crowdsourcing that can complement LUCAS. We compared the results between the FotoQuest campaigns in 2015 and 2018 and found a significant improvement in 2018, i.e., a much higher match of LC between FotoQuest Go Europe and LUCAS. As shown by the cost comparisons with LUCAS, FotoQuest can complement LUCAS surveys by enabling continuous collection of large amounts of high quality, spatially explicit field data at a low cost.